Lune

学者档案2020-2026

Yang Gao

Nanjing University

41论文数
36末位作者
85合作者人数
0一作
0独著

一作与末位作者按论文署名顺序统计,部分顶会采用姓氏字母顺序署名。

近期论文41

  1. Distractor-free Generalizable 3D Gaussian Splatting第 4 位,共 4 位作者ICLR 2026 · 9 次引用
  2. Furina: Fragmented Uncertainty-Driven Refusal Instability Attack第 3 位,共 3 位作者ICML 2026 · 1 次引用
  3. ManiLong-Shot: Interaction-Aware One-Shot Imitation Learning for Long-Horizon Manipulation第 6 位,共 6 位作者AAAI 2026 · 1 次引用
  4. A Faster Parameter-Free Regret Matching Algorithm第 6 位,共 6 位作者ICLR 2026
  5. AGiLe: Learning Robust Long-Horizon Manipulation via Affordance-Grounded Bidirectional Latent Planning第 6 位,共 6 位作者CVPR 2026
  6. Faster Game Solving via Asymmetry of Step Sizes第 5 位,共 5 位作者AAAI 2026
  7. Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning第 11 位,共 11 位作者ACL 2026
  8. Multi-Agent Reinforcement Learning with Communication-Constrained Priors第 7 位,共 7 位作者NeurIPS 2025 · 9 次引用
  9. Federated Multi-armed Bandits with Efficient Bit-Level Communications第 7 位,共 7 位作者NeurIPS 2025 · 6 次引用
  10. Last-Iterate Convergence of Smooth Regret Matching+^+ Variants in Learning Nash Equilibria第 8 位,共 8 位作者NeurIPS 2025 · 3 次引用
  11. Towards Perfection: Building Inter-component Mutual Correction for Retinex-based Low-light Image Enhancement第 7 位,共 7 位作者ACM MM 2025 · 3 次引用
  12. CoT-VTM: Visual-to-Music Generation with Chain-of-Thought Reasoning第 5 位,共 5 位作者ACL Findings 2025 · 2 次引用
  13. In-Context Fully Decentralized Cooperative Multi-Agent Reinforcement Learning第 3 位,共 3 位作者NeurIPS 2025 · 2 次引用
  14. Beyond Mandatory Federations: Balancing Egoism, Utilitarianism and Egalitarianism in Mixed-Motive Games第 6 位,共 6 位作者AAAI 2025 · 1 次引用
  15. Combinatorial Ski Rental Problem: Robust and Learning-Augmented Algorithms第 7 位,共 7 位作者NeurIPS 2025 · 1 次引用
  16. Efficient Last-Iterate Convergence in Solving Extensive-Form Games第 9 位,共 9 位作者NeurIPS 2025 · 1 次引用
  17. GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation第 7 位,共 7 位作者ICLR 2025
  18. Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD第 6 位,共 6 位作者ICLR 2025
  19. SCaR: Refining Skill Chaining for Long-Horizon Robotic Manipulation via Dual Regularization第 4 位,共 4 位作者NeurIPS 2024 · 26 次引用
  20. PG-LBO: Enhancing High-Dimensional Bayesian Optimization with Pseudo-Label and Gaussian Process Guidance第 6 位,共 6 位作者AAAI 2024 · 12 次引用
  21. InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules第 6 位,共 6 位作者ICLR 2024 · 7 次引用
  22. START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation第 4 位,共 4 位作者NeurIPS 2024 · 6 次引用
  23. Optimistic Value Instructors for Cooperative Multi-Agent Reinforcement Learning第 9 位,共 9 位作者AAAI 2024 · 4 次引用
  24. Hybrid Sharing for Multi-Label Image Classification第 4 位,共 5 位作者ICLR 2024 · 3 次引用
  25. Safe and Robust Subgame Exploitation in Imperfect Information Games第 7 位,共 7 位作者ICML 2024 · 3 次引用
  26. Diving Segmentation Model into Pixels第 4 位,共 5 位作者ICLR 2024
  27. Enhanced Tensor Low-Rank and Sparse Representation Recovery for Incomplete Multi-View Clustering第 5 位,共 6 位作者AAAI 2023 · 83 次引用
  28. DomainAdaptor: A Novel Approach to Test-time Adaptation第 4 位,共 4 位作者ICCV 2023 · 31 次引用
  29. Learning Explicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning via Polarization Policy Gradient第 5 位,共 5 位作者AAAI 2023 · 11 次引用
  30. An Efficient Deep Reinforcement Learning Algorithm for Solving Imperfect Information Extensive-Form Games第 5 位,共 5 位作者AAAI 2023 · 8 次引用

展示最近收录的 30 篇论文。

黄昏的海面,两侧是细线勾勒的悬崖